eng-jagoy-t5-001 / README.md
tarsssss's picture
Training in progress epoch 67
f5772ed
|
raw
history blame
4.06 kB
metadata
license: apache-2.0
base_model: t5-small
tags:
  - generated_from_keras_callback
model-index:
  - name: tarsssss/eng-jagoy-t5-001
    results: []

tarsssss/eng-jagoy-t5-001

This model is a fine-tuned version of t5-small on an unknown dataset. It achieves the following results on the evaluation set:

  • Train Loss: 5.3469
  • Validation Loss: 5.4001
  • Epoch: 67

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

  • optimizer: {'name': 'AdamWeightDecay', 'learning_rate': 2e-05, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False, 'weight_decay_rate': 0.01}
  • training_precision: float32

Training results

Train Loss Validation Loss Epoch
7.8603 7.4105 0
7.3775 7.1273 1
7.1632 6.9598 2
7.0228 6.8372 3
6.9085 6.7335 4
6.8226 6.6458 5
6.7451 6.5671 6
6.6785 6.5022 7
6.6254 6.4409 8
6.5606 6.3842 9
6.5163 6.3361 10
6.4682 6.2908 11
6.4250 6.2436 12
6.3749 6.1907 13
6.3293 6.1494 14
6.2822 6.1098 15
6.2560 6.0750 16
6.2078 6.0508 17
6.1839 6.0229 18
6.1561 5.9944 19
6.1146 5.9732 20
6.0885 5.9490 21
6.0587 5.9243 22
6.0366 5.9064 23
6.0135 5.8857 24
5.9904 5.8675 25
5.9681 5.8482 26
5.9473 5.8262 27
5.9263 5.8127 28
5.9031 5.7896 29
5.8827 5.7721 30
5.8566 5.7482 31
5.8406 5.7355 32
5.8285 5.7231 33
5.7944 5.7049 34
5.7822 5.6968 35
5.7567 5.6813 36
5.7526 5.6650 37
5.7363 5.6614 38
5.7132 5.6398 39
5.6945 5.6383 40
5.6786 5.6243 41
5.6636 5.6071 42
5.6527 5.5955 43
5.6390 5.5876 44
5.6198 5.5754 45
5.6082 5.5663 46
5.6070 5.5572 47
5.5782 5.5493 48
5.5679 5.5487 49
5.5520 5.5301 50
5.5307 5.5261 51
5.5284 5.5089 52
5.5160 5.5003 53
5.4976 5.4981 54
5.4864 5.4860 55
5.4795 5.4816 56
5.4653 5.4652 57
5.4484 5.4639 58
5.4335 5.4580 59
5.4231 5.4454 60
5.4132 5.4358 61
5.4064 5.4349 62
5.3886 5.4261 63
5.3913 5.4193 64
5.3692 5.4138 65
5.3556 5.4028 66
5.3469 5.4001 67

Framework versions

  • Transformers 4.33.2
  • TensorFlow 2.10.0
  • Datasets 2.15.0
  • Tokenizers 0.13.3